Budgetary: estimate token spend MCP Server
io.github.thriftell/budgetary
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Budgetary: estimate token spend MCP server?
Pre-flight token-spend estimate (range, scenario, confidence) for a coding task, or an abstention.
How to install Budgetary: estimate token spend
Copy-paste configuration for popular MCP clients.
BUDGETARY_API_KEYrequiredsecretBudgetary API key (bg_live_ or bg_test_ prefix). Get one at https://budgetary.tools.
BUDGETARY_HOSTOptional tag naming the MCP host this server runs under — e.g. claude-code, cursor, codex, copilot. It labels each estimate with where it came from, and an explicit value overrides the host name the MCP handshake reports. Free-form; defaults to "mcp" when unset.
{
"mcpServers": {
"budgetary": {
"command": "npx",
"args": [
"-y",
"@budgetary/mcp"
],
"env": {
"BUDGETARY_API_KEY": "<YOUR_BUDGETARY_API_KEY>",
"BUDGETARY_HOST": "<YOUR_BUDGETARY_HOST>"
}
}
}
}Related MCP servers

io.github.thuupx/lunge
Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections
Repo intelligence: triage, fix PRs, SARIF reachability, recall. Free codna login to execute.
View repository →Manage WiseWall sites from an AI coding assistant — deploy, configure DNS, secrets, and plans.

OpenAPI lifecycle guard and MCP sidecar for policy-driven API orchestration.

AI-powered web scraping with Markdown conversion and structured JSON Schema extraction.

AI-powered web scraping with Markdown distillation and JSON Schema extraction.
